Praveen Niranda, Peter T. McKenney, Guifang Fustat.ME stat.ML
Learning a dynamical system and reconstructing the underlying regulatory network from $p$ discretely observed state trajectories remain challenging problems. Existing approaches often produced a large number of spurious edges and suffered from several methodological limitations. We propose a new approach, Reconstruction of Enhanced Causal Omnidirectional Network (RECON), that leverages an integral-based additive nonparametric ODE model to reconstruct regulatory networks from $p$ time-course data. RECON incorporates five methodological advances. First, it incorporates a new data-driven edge selection procedure that substantially reduces spurious edges while preserving true regulatory edges. Second, it reconstructs an omnidirectional network that captures causal regulatory relationships rather than merely statistical associations or noise artifacts. Third, it substantially broadens the applicability of standard ODE-based approaches by accommodating both dense regular and sparse irregular longitudinal sampling scenarios. Fourth, it models both node trajectories and edge regulatory effects as time-varying functions, emphasizing a dynamic regulatory network. Fifth, it reconstructs a signed and weighted regulatory network and provides comprehensive network interpretation through two-way direction, activatory/inhibitory indicator, and strength, together with keystone node identification and topological structure. Across five simulation studies, RECON consistently outperforms GRADE by removing nearly all spurious edges while retaining nearly all true regulatory edges, resulting in highly accurate network reconstruction. In the most challenging scenario, the number of spurious edges is reduced from 239 to 0.
Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computation: the dense network cannot be retained on-chip, and every parameter must be loaded for every input. Existing model compression reduces this transfer only at the cost of permanent capacity loss. We propose Sigma-Branch (SigmaB), a framework that restructures a pretrained dense network into a hierarchical binary tree composed of a shared backbone, hierarchical routers, and specialized leaves. Pretrained weights are distributed across the tree via activation-based spherical k-means clustering, which jointly initializes router weights and per-branch channel allocations; soft-routing fine-tuning then aligns each leaf with its routed input subset. At inference, the resulting network executes only a single root-to-leaf path, reducing the active-parameter footprint while storing the complete dense parameter set in memory. Across CIFAR-100 / ResNet-50, ImageNet-1K / ResNet-50, and ModelNet40 / PointNet++, SigmaB-Net reduces per-inference active parameters by 58-60% while remaining within 1.72 percentage points (pp) of the dense baseline Top-1. At comparable ImageNet-1K Top-1, the active-parameter reduction exceeds static structured pruning (FPGM, HRank) by 14-23 pp. The cross-modal evaluation, spanning 2D vision and 3D point-cloud backbones, substantiates a framework-level claim that decouples per-inference memory traffic from the total parameter count.